self-conscious - Story 126879 | Emotion Vectors in Gemma4-31B

A wave of nausea washed over Eva as she saw her poetry, printed on posters, plastered across the university campus. The poems, personal and raw, had been posted anonymously online. Now, they were public, and she couldn't escape the exposure. She pressed a hand against her stomach.

The world seemed to shrink around her as she walked down the hall, avoiding eye contact with everyone. Every passing glance felt like a personal critique. She felt her hands trembling.

She quickened her pace, desperate to be somewhere, anywhere, else.

Emotion: self-conscious

Cluster: Embarrassment

PC1 (Valence): -1.03 Negative

PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238